基于贝叶斯模型加权平均方法的水文模型不确定性分析

Uncertainty analysis of hydrological modeling using the Bayesian Model Averaging Method

贝叶斯模型加权平均(BMA)方法是通过综合几个模型预报值的后验分布来推断预报量的更可靠概率分布分析工具。它不仅能提供一个综合的预报值,还能提供一个综合的预报区间。本文采用3个水文模型,统一用SCE-UA算法率定参数,得到3组不同的预报值用于BMA方法的综合,着重分析比较BMA和单个模型的预报不确定性区间,来检验贝叶斯模型加权平均方法是否能提高预报的可靠性。结果表明,BMA方法不仅能提高预报精度,还能推求出性质更为优良的预报区间,提高预报的可靠性。

Bayesian Model Averaging（BMA） method is a tool to infer the statistical distribution of a quantity to be predicted as the mixture of a set of individual prediction distributions,with each individual prediction distribution constructed on the basis of the performance of each different model.It can combine the forecasts of different models together to generate a new forecast,and it can also provide the predication interval.In this paper,three hydrological models are calibrated by SCE-UA method to provide three different forecasts for BMA combination,and the research focus in this study is shifted onto the comparison of the prediction uncertainty interval generated by the BMA with that of each individual model,in order to see if the BMA can improve the prediction reliability.It is found that the BMA method can not only improve the flow prediction efficiency,but also can derive more accurate prediction interval to improve the reliance of the prediction.